While studying riscv's cmpxchg.h file, I got really interested in
understanding how RISCV asm implemented the different versions of
{cmp,}xchg.
When I understood the pattern, it made sense for me to remove the
duplications and create macros to make it easier to understand what exactly
changes between the versions: Instruction sufixes & barriers.
Also, did the same kind of work on atomic.c.
After that, I noted both cmpxchg and xchg only accept variables of
size 4 and 8, compared to x86 and arm64 which do 1,2,4,8.
Now that deduplication is done, it is quite direct to implement them
for variable sizes 1 and 2, so I did it. Then Guo Ren already presented
me some possible users :)
I did compare the generated asm on a test.c that contained usage for every
changed function, and could not detect any change on patches 1 + 2 + 3
compared with upstream.
Pathes 4 & 5 were compiled-tested, but I could not run-test them yet.
Thanks!
Leo
Changes since squashed cmpxchg RFCv2:
- Removed rc parameter from the new macro: it can be internal to the macro
- 2 new patches: cmpxchg size 1 and 2, xchg size 1 and 2
https://lore.kernel.org/all/[email protected]/
Changes since squashed cmpxchg RFCv1:
- Unified with atomic.c patchset
- Rebased on top of torvalds/master (thanks Andrea Parri!)
- Removed helper macros that were not being used elsewhere in the kernel.
https://lore.kernel.org/all/[email protected]/
https://lore.kernel.org/all/[email protected]/
Changes since (cmpxchg) RFCv3:
- Squashed the 6 original patches in 2: one for cmpxchg and one for xchg
https://lore.kernel.org/all/[email protected]/
Changes since (cmpxchg) RFCv2:
- Fixed macros that depend on having a local variable with a magic name
- Previous cast to (long) is now only applied on 4-bytes cmpxchg
https://lore.kernel.org/all/[email protected]/
Changes since (cmpxchg) RFCv1:
- Fixed patch 4/6 suffix from 'w.aqrl' to '.w.aqrl', to avoid build error
https://lore.kernel.org/all/[email protected]/
Leonardo Bras (5):
riscv/cmpxchg: Deduplicate xchg() asm functions
riscv/cmpxchg: Deduplicate cmpxchg() asm and macros
riscv/atomic.h : Deduplicate arch_atomic.*
riscv/cmpxchg: Implement cmpxchg for variables of size 1 and 2
riscv/cmpxchg: Implement xchg for variables of size 1 and 2
arch/riscv/include/asm/atomic.h | 164 ++++++-------
arch/riscv/include/asm/cmpxchg.h | 393 ++++++++++---------------------
2 files changed, 195 insertions(+), 362 deletions(-)
--
2.41.0
Some functions use mostly the same asm for 32-bit and 64-bit versions.
Make a macro that is generic enough and avoid code duplication.
(This did not cause any change in generated asm)
Signed-off-by: Leonardo Bras <[email protected]>
Reviewed-by: Guo Ren <[email protected]>
Reviewed-by: Andrea Parri <[email protected]>
---
arch/riscv/include/asm/atomic.h | 164 +++++++++++++++-----------------
1 file changed, 76 insertions(+), 88 deletions(-)
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index f5dfef6c2153..80cca7ac16fd 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -196,22 +196,28 @@ ATOMIC_OPS(xor, xor, i)
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
+#define _arch_atomic_fetch_add_unless(_prev, _rc, counter, _a, _u, sfx) \
+({ \
+ __asm__ __volatile__ ( \
+ "0: lr." sfx " %[p], %[c]\n" \
+ " beq %[p], %[u], 1f\n" \
+ " add %[rc], %[p], %[a]\n" \
+ " sc." sfx ".rl %[rc], %[rc], %[c]\n" \
+ " bnez %[rc], 0b\n" \
+ " fence rw, rw\n" \
+ "1:\n" \
+ : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \
+ : [a]"r" (_a), [u]"r" (_u) \
+ : "memory"); \
+})
+
/* This is required to provide a full barrier on success. */
static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int prev, rc;
- __asm__ __volatile__ (
- "0: lr.w %[p], %[c]\n"
- " beq %[p], %[u], 1f\n"
- " add %[rc], %[p], %[a]\n"
- " sc.w.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- : [a]"r" (a), [u]"r" (u)
- : "memory");
+ _arch_atomic_fetch_add_unless(prev, rc, v->counter, a, u, "w");
+
return prev;
}
#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
@@ -222,77 +228,86 @@ static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a,
s64 prev;
long rc;
- __asm__ __volatile__ (
- "0: lr.d %[p], %[c]\n"
- " beq %[p], %[u], 1f\n"
- " add %[rc], %[p], %[a]\n"
- " sc.d.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- : [a]"r" (a), [u]"r" (u)
- : "memory");
+ _arch_atomic_fetch_add_unless(prev, rc, v->counter, a, u, "d");
+
return prev;
}
#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
#endif
+#define _arch_atomic_inc_unless_negative(_prev, _rc, counter, sfx) \
+({ \
+ __asm__ __volatile__ ( \
+ "0: lr." sfx " %[p], %[c]\n" \
+ " bltz %[p], 1f\n" \
+ " addi %[rc], %[p], 1\n" \
+ " sc." sfx ".rl %[rc], %[rc], %[c]\n" \
+ " bnez %[rc], 0b\n" \
+ " fence rw, rw\n" \
+ "1:\n" \
+ : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \
+ : \
+ : "memory"); \
+})
+
static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v)
{
int prev, rc;
- __asm__ __volatile__ (
- "0: lr.w %[p], %[c]\n"
- " bltz %[p], 1f\n"
- " addi %[rc], %[p], 1\n"
- " sc.w.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_inc_unless_negative(prev, rc, v->counter, "w");
+
return !(prev < 0);
}
#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative
+#define _arch_atomic_dec_unless_positive(_prev, _rc, counter, sfx) \
+({ \
+ __asm__ __volatile__ ( \
+ "0: lr." sfx " %[p], %[c]\n" \
+ " bgtz %[p], 1f\n" \
+ " addi %[rc], %[p], -1\n" \
+ " sc." sfx ".rl %[rc], %[rc], %[c]\n" \
+ " bnez %[rc], 0b\n" \
+ " fence rw, rw\n" \
+ "1:\n" \
+ : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \
+ : \
+ : "memory"); \
+})
+
static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v)
{
int prev, rc;
- __asm__ __volatile__ (
- "0: lr.w %[p], %[c]\n"
- " bgtz %[p], 1f\n"
- " addi %[rc], %[p], -1\n"
- " sc.w.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_dec_unless_positive(prev, rc, v->counter, "w");
+
return !(prev > 0);
}
#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive
+#define _arch_atomic_dec_if_positive(_prev, _rc, counter, sfx) \
+({ \
+ __asm__ __volatile__ ( \
+ "0: lr." sfx " %[p], %[c]\n" \
+ " addi %[rc], %[p], -1\n" \
+ " bltz %[rc], 1f\n" \
+ " sc." sfx ".rl %[rc], %[rc], %[c]\n" \
+ " bnez %[rc], 0b\n" \
+ " fence rw, rw\n" \
+ "1:\n" \
+ : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \
+ : \
+ : "memory"); \
+})
+
static __always_inline int arch_atomic_dec_if_positive(atomic_t *v)
{
int prev, rc;
- __asm__ __volatile__ (
- "0: lr.w %[p], %[c]\n"
- " addi %[rc], %[p], -1\n"
- " bltz %[rc], 1f\n"
- " sc.w.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_dec_if_positive(prev, rc, v->counter, "w");
+
return prev - 1;
}
@@ -304,17 +319,8 @@ static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v)
s64 prev;
long rc;
- __asm__ __volatile__ (
- "0: lr.d %[p], %[c]\n"
- " bltz %[p], 1f\n"
- " addi %[rc], %[p], 1\n"
- " sc.d.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_inc_unless_negative(prev, rc, v->counter, "d");
+
return !(prev < 0);
}
@@ -325,17 +331,8 @@ static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v)
s64 prev;
long rc;
- __asm__ __volatile__ (
- "0: lr.d %[p], %[c]\n"
- " bgtz %[p], 1f\n"
- " addi %[rc], %[p], -1\n"
- " sc.d.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_dec_unless_positive(prev, rc, v->counter, "d");
+
return !(prev > 0);
}
@@ -346,17 +343,8 @@ static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
s64 prev;
long rc;
- __asm__ __volatile__ (
- "0: lr.d %[p], %[c]\n"
- " addi %[rc], %[p], -1\n"
- " bltz %[rc], 1f\n"
- " sc.d.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_dec_if_positive(prev, rc, v->counter, "d");
+
return prev - 1;
}
--
2.41.0
In this header every xchg define (_relaxed, _acquire, _release, vanilla)
contain it's own asm file, both for 4-byte variables an 8-byte variables,
on a total of 8 versions of mostly the same asm.
This is usually bad, as it means any change may be done in up to 8
different places.
Unify those versions by creating a new define with enough parameters to
generate any version of the previous 8.
Then unify the result under a more general define, and simplify
arch_xchg* generation.
(This did not cause any change in generated asm)
Signed-off-by: Leonardo Bras <[email protected]>
Reviewed-by: Andrea Parri <[email protected]>
---
arch/riscv/include/asm/cmpxchg.h | 136 +++++--------------------------
1 file changed, 22 insertions(+), 114 deletions(-)
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 2f4726d3cfcc..ec4ea4f3f908 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -11,60 +11,30 @@
#include <asm/barrier.h>
#include <asm/fence.h>
-#define __xchg_relaxed(ptr, new, size) \
+#define __arch_xchg(sfx, prepend, append, r, p, n) \
({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(new) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- " amoswap.w %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- " amoswap.d %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
-
-#define arch_xchg_relaxed(ptr, x) \
-({ \
- __typeof__(*(ptr)) _x_ = (x); \
- (__typeof__(*(ptr))) __xchg_relaxed((ptr), \
- _x_, sizeof(*(ptr))); \
+ __asm__ __volatile__ ( \
+ prepend \
+ " amoswap" sfx " %0, %2, %1\n" \
+ append \
+ : "=r" (r), "+A" (*(p)) \
+ : "r" (n) \
+ : "memory"); \
})
-#define __xchg_acquire(ptr, new, size) \
+#define _arch_xchg(ptr, new, sfx, prepend, append) \
({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(new) __new = (new); \
+ __typeof__(*(ptr)) __new = (new); \
__typeof__(*(ptr)) __ret; \
- switch (size) { \
+ __typeof__(ptr) __ptr = (ptr); \
+ switch (sizeof(*__ptr)) { \
case 4: \
- __asm__ __volatile__ ( \
- " amoswap.w %0, %2, %1\n" \
- RISCV_ACQUIRE_BARRIER \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
+ __arch_xchg(".w" sfx, prepend, append, \
+ __ret, __ptr, __new); \
break; \
case 8: \
- __asm__ __volatile__ ( \
- " amoswap.d %0, %2, %1\n" \
- RISCV_ACQUIRE_BARRIER \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
+ __arch_xchg(".d" sfx, prepend, append, \
+ __ret, __ptr, __new); \
break; \
default: \
BUILD_BUG(); \
@@ -72,79 +42,17 @@
__ret; \
})
-#define arch_xchg_acquire(ptr, x) \
-({ \
- __typeof__(*(ptr)) _x_ = (x); \
- (__typeof__(*(ptr))) __xchg_acquire((ptr), \
- _x_, sizeof(*(ptr))); \
-})
+#define arch_xchg_relaxed(ptr, x) \
+ _arch_xchg(ptr, x, "", "", "")
-#define __xchg_release(ptr, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(new) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- RISCV_RELEASE_BARRIER \
- " amoswap.w %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- RISCV_RELEASE_BARRIER \
- " amoswap.d %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
+#define arch_xchg_acquire(ptr, x) \
+ _arch_xchg(ptr, x, "", "", RISCV_ACQUIRE_BARRIER)
#define arch_xchg_release(ptr, x) \
-({ \
- __typeof__(*(ptr)) _x_ = (x); \
- (__typeof__(*(ptr))) __xchg_release((ptr), \
- _x_, sizeof(*(ptr))); \
-})
-
-#define __arch_xchg(ptr, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(new) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- " amoswap.w.aqrl %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- " amoswap.d.aqrl %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
+ _arch_xchg(ptr, x, "", RISCV_RELEASE_BARRIER, "")
#define arch_xchg(ptr, x) \
-({ \
- __typeof__(*(ptr)) _x_ = (x); \
- (__typeof__(*(ptr))) __arch_xchg((ptr), _x_, sizeof(*(ptr))); \
-})
+ _arch_xchg(ptr, x, ".aqrl", "", "")
#define xchg32(ptr, x) \
({ \
--
2.41.0
In this header every cmpxchg define (_relaxed, _acquire, _release,
vanilla) contain it's own asm file, both for 4-byte variables an 8-byte
variables, on a total of 8 versions of mostly the same asm.
This is usually bad, as it means any change may be done in up to 8
different places.
Unify those versions by creating a new define with enough parameters to
generate any version of the previous 8.
Then unify the result under a more general define, and simplify
arch_cmpxchg* generation
(This did not cause any change in generated asm)
Signed-off-by: Leonardo Bras <[email protected]>
Reviewed-by: Andrea Parri <[email protected]>
---
arch/riscv/include/asm/cmpxchg.h | 187 +++++--------------------------
1 file changed, 29 insertions(+), 158 deletions(-)
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index ec4ea4f3f908..5a07646fae65 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -71,127 +71,40 @@
* store NEW in MEM. Return the initial value in MEM. Success is
* indicated by comparing RETURN with OLD.
*/
-#define __cmpxchg_relaxed(ptr, old, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- register unsigned int __rc; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- "0: lr.w %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.w %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" ((long)__old), "rJ" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- "0: lr.d %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.d %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" (__old), "rJ" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
-#define arch_cmpxchg_relaxed(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) _o_ = (o); \
- __typeof__(*(ptr)) _n_ = (n); \
- (__typeof__(*(ptr))) __cmpxchg_relaxed((ptr), \
- _o_, _n_, sizeof(*(ptr))); \
-})
-#define __cmpxchg_acquire(ptr, old, new, size) \
+#define __arch_cmpxchg(lr_sfx, sc_sfx, prepend, append, r, p, co, o, n) \
({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __typeof__(*(ptr)) __ret; \
register unsigned int __rc; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- "0: lr.w %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.w %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- RISCV_ACQUIRE_BARRIER \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" ((long)__old), "rJ" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- "0: lr.d %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.d %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- RISCV_ACQUIRE_BARRIER \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" (__old), "rJ" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
-
-#define arch_cmpxchg_acquire(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) _o_ = (o); \
- __typeof__(*(ptr)) _n_ = (n); \
- (__typeof__(*(ptr))) __cmpxchg_acquire((ptr), \
- _o_, _n_, sizeof(*(ptr))); \
+ \
+ __asm__ __volatile__ ( \
+ prepend \
+ "0: lr" lr_sfx " %0, %2\n" \
+ " bne %0, %z3, 1f\n" \
+ " sc" sc_sfx " %1, %z4, %2\n" \
+ " bnez %1, 0b\n" \
+ append \
+ "1:\n" \
+ : "=&r" (r), "=&r" (__rc), "+A" (*(p)) \
+ : "rJ" (co o), "rJ" (n) \
+ : "memory"); \
})
-#define __cmpxchg_release(ptr, old, new, size) \
+#define _arch_cmpxchg(ptr, old, new, sc_sfx, prepend, append) \
({ \
__typeof__(ptr) __ptr = (ptr); \
__typeof__(*(ptr)) __old = (old); \
__typeof__(*(ptr)) __new = (new); \
__typeof__(*(ptr)) __ret; \
- register unsigned int __rc; \
- switch (size) { \
+ \
+ switch (sizeof(*__ptr)) { \
case 4: \
- __asm__ __volatile__ ( \
- RISCV_RELEASE_BARRIER \
- "0: lr.w %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.w %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" ((long)__old), "rJ" (__new) \
- : "memory"); \
+ __arch_cmpxchg(".w", ".w" sc_sfx, prepend, append, \
+ __ret, __ptr, (long), __old, __new); \
break; \
case 8: \
- __asm__ __volatile__ ( \
- RISCV_RELEASE_BARRIER \
- "0: lr.d %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.d %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" (__old), "rJ" (__new) \
- : "memory"); \
+ __arch_cmpxchg(".d", ".d" sc_sfx, prepend, append, \
+ __ret, __ptr, /**/, __old, __new); \
break; \
default: \
BUILD_BUG(); \
@@ -199,62 +112,20 @@
__ret; \
})
-#define arch_cmpxchg_release(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) _o_ = (o); \
- __typeof__(*(ptr)) _n_ = (n); \
- (__typeof__(*(ptr))) __cmpxchg_release((ptr), \
- _o_, _n_, sizeof(*(ptr))); \
-})
+#define arch_cmpxchg_relaxed(ptr, o, n) \
+ _arch_cmpxchg((ptr), (o), (n), "", "", "")
-#define __cmpxchg(ptr, old, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- register unsigned int __rc; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- "0: lr.w %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.w.rl %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- " fence rw, rw\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" ((long)__old), "rJ" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- "0: lr.d %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.d.rl %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- " fence rw, rw\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" (__old), "rJ" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
+#define arch_cmpxchg_acquire(ptr, o, n) \
+ _arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER)
+
+#define arch_cmpxchg_release(ptr, o, n) \
+ _arch_cmpxchg((ptr), (o), (n), "", RISCV_RELEASE_BARRIER, "")
#define arch_cmpxchg(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) _o_ = (o); \
- __typeof__(*(ptr)) _n_ = (n); \
- (__typeof__(*(ptr))) __cmpxchg((ptr), \
- _o_, _n_, sizeof(*(ptr))); \
-})
+ _arch_cmpxchg((ptr), (o), (n), ".rl", "", " fence rw, rw\n")
#define arch_cmpxchg_local(ptr, o, n) \
- (__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
+ arch_cmpxchg_relaxed((ptr), (o), (n))
#define arch_cmpxchg64(ptr, o, n) \
({ \
--
2.41.0